Skip to content

Gemini 3.5 Flash-Lite - Free Low-Latency Multimodal Model, 1M Context

Model ID gemini-3.5-flash-lite
This is a Gemini API free-tier model: no credit card required, but inputs and outputs are used by Google to improve its products, and rate limits are lower than on the paid tier.

Model Information

AttributeValue
Context length1,048,576 tokens
Max output65,536 tokens
Input price$0 (free tier)
Output price$0 (free tier)
ProviderGoogle DeepMind
StatusAvailable on the free tier
Input modalitiesText, image, video, audio, PDF
Release date2026-07

Description

Gemini 3.5 Flash-Lite is designed for high-throughput, low-cost scenarios, with official typical uses including sub-agent tasks, document parsing, simple data extraction, and batch translation. Although it is positioned as a lightweight model, it still offers a 1-million-token context window and a max output of 65,536 tokens.

It supports function calling, structured output, thinking levels, and URL context, making it suitable for task routing, classifiers, or large-batch text processing. The free tier does not provide Batch or Context Caching.

Usage Example

curl https://generativelanguage.googleapis.com/v1beta/openai/chat/completions \
  -H "Authorization: Bearer $GEMINI_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "gemini-3.5-flash-lite",
    "messages": [{"role": "user", "content": "Classify this user review as positive, neutral, or negative"}]
  }'

Related Links

📚 Related Free Models

These models are also available for $0 on Gemini. Choose by context length and modality.

ModelContextDescription
Gemini 4 Hydrogen1MGemini 4 Hydrogen is Google’s free-tier flagship model
Gemini 3.6 Flash1MGoogle’s previous-generation Flash multimodal model
Gemini 3.8 Flash1MGoogle’s latest Flash multimodal model, built for

📋 View all Gemini free models →

🔗 Site Navigation

Last updated on · Source: Gemini official documentation and pricing pages. Quotas and prices may change at any time.